Abstract
We present a simple, efficient, and scalable unfolding network, SAUNet, to simplify the network design with an adaptive alternate optimization framework for hyperspectral image (HSI) reconstruction. SAUNet customizes a Residual Adaptive ADMM Framework (R2ADMM) to connect each stage of the network via a group of learnable parameters to promote the usage of mask prior, which greatly stabilizes training and solves the accuracy degradation issue. Additionally, we introduce a simple convolutional modulation block (CMB), which leads to efficient training, easy scale-up, and less computation. Coupling these two designs, SAUNet can be scaled to non-trivial 13 stages with continuous improvement. Without bells and whistles, SAUNet improves both performance and speed compared with the previous state-of-the-art counterparts, which makes it feasible for practical high-resolution HSI reconstruction scenarios. We set new records on CAVE and KAIST HSI reconstruction benchmarks. Code and models are available at this https URL.
Abstract (translated)
我们介绍了一个简单、高效、可扩展的展开网络SAUNet,以简化超分辨率图像(HSI)重建网络的设计,采用自适应交替优化框架。SAUNet定制了Residual Adaptive ADMM框架(R2ADMM),通过一组可学习参数连接网络的各个阶段,促进使用先验掩模,极大地稳定了训练和解决精度下降问题。此外,我们引入了一个简单的卷积调制块(CMB),导致高效的训练、容易扩展和较少的计算。结合这两个设计,SAUNet可以无限地扩展到重要的13个阶段,并保持不断改进。相比之前的最先进的 counterpart,SAUNet在性能和速度方面都取得了改进,使其适用于实际的高分辨率HSI重建场景。我们在CAVE和KAIST HSI重建基准数据上创造了新的记录。代码和模型可在该httpsURL上获取。
URL
https://arxiv.org/abs/2301.10208